Transfer Learning by Discovering Latent Task Parametrizations
作者： G.D. Konidaris , F. Doshi-Velez
DOI:
关键词:
摘要: We present a framework that is able to discover the latent factors parametrize family of related tasks from data. The resulting model rapidly identify dynamics new task instance, allowing an agent flexibly adapt variations.
参考文章(17)
Yee Whye Teh, Matthias Seeger, Michael I Jordan, None, Semiparametric Latent Factor Models international conference on artificial intelligence and statistics. ,(2005)
Alessandro Lazaric, Marcello Restelli, Eliseo Ferrante, Transfer of task representation in reinforcement learning using policy-based proto-value functions adaptive agents and multi-agents systems. ,vol. 3, pp. 1329- 1332 ,(2008) , 10.5555/1402821.1402864
Kimberly Ferguson, Sridhar Mahadevan, Proto-transfer Learning in Markov Decision Processes Using Spectral Methods ,(2006)
Jens Kober, Andreas Wilhelm, Erhan Oztop, Jan Peters, Reinforcement learning to adjust parametrized motor primitives to new situations Autonomous Robots. ,vol. 33, pp. 361- 379 ,(2012) , 10.1007/S10514-012-9290-3
Peter Stone, Matthew E. Taylor, Transfer Learning for Reinforcement Learning Domains: A Survey Journal of Machine Learning Research. ,vol. 10, pp. 1633- 1685 ,(2009) , 10.5555/1577069.1755839
Stephane Ross, Brahim Chaib-draa, Joelle Pineau, Bayesian reinforcement learning in continuous POMDPs with application to robot navigation international conference on robotics and automation. pp. 2845- 2851 ,(2008) , 10.1109/ROBOT.2008.4543641
Pascal Poupart, Nikos Vlassis, Jesse Hoey, Kevin Regan, An analytic solution to discrete Bayesian reinforcement learning Proceedings of the 23rd international conference on Machine learning - ICML '06. pp. 697- 704 ,(2006) , 10.1145/1143844.1143932
Andrew G. Barto, Robert H. Crites, Improving Elevator Performance Using Reinforcement Learning neural information processing systems. ,vol. 8, pp. 1017- 1023 ,(1995)
A.G. Barto, R.S. Sutton, Reinforcement Learning: An Introduction ,(1988)
Michael L. Littman, David Wingate, John Asmuth, Ali Nouri, Lihong Li, A Bayesian sampling approach to exploration in reinforcement learning uncertainty in artificial intelligence. pp. 19- 26 ,(2009)